Learning to Represent Edits

Pengcheng Yin, Graham Neubig, Miltiadis Allamanis, Marc Brockschmidt, Alexander L. Gaunt

Keywords: Representation Learning, Source Code, Natural Language, edit

Abstract:

We introduce the problem of learning distributed representations of edits. By combining a
"neural editor" with an "edit encoder", our models learn to represent the salient
information of an edit and can be used to apply edits to new inputs.
We experiment on natural language and source code edit data. Our evaluation yields
promising results that suggest that our neural network models learn to capture
the structure and semantics of edits. We hope that this interesting task and
data source will inspire other researchers to work further on this problem.

Code: [ Microsoft/msrc-dpu-learning-to-represent-edits](https://github.com/Microsoft/msrc-dpu-learning-to-represent-edits) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=BJl6AjC5F7)

Data: [WikiAtomicEdits](https://paperswithcode.com/dataset/wikiatomicedits)